获取记录分享链接
AI agents call getRecordShareLink to retrieve information from MCP Mingdao without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or generates a share link for an existing record, which is a read operation that queries data and produces a URL for sharing purposes. It has no side effects on the record itself, no financial implications, and does not execute arbitrary code or delete data. The minimal blast radius if misused would be unauthorized exposure of a share link.
From the tool's definition Tool name 'getRecordShareLink' and description '获取记录分享链接' (get record share link) indicate retrieval of a sharing URL without modifying data.
Attacks that exploit this kind of access
获取记录分享链接. It is categorised as a Read tool in the MCP Mingdao MCP Server, which means it retrieves data without modifying state.
Register the MCP Mingdao MCP server in PolicyLayer and add a rule for getRecordShareLink: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Mingdao. Nothing to install.
getRecordShareLink is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the getRecordShareLink rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for getRecordShareLink. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
getRecordShareLink is provided by the MCP Mingdao MCP server (mingdaocloud/mcp-mingdao). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →